Particulate Monitoring and Evaluation of the Low-cost Sensors Performance at the Middle East

Key Words: Air Quality; Air Pollution Monitoring; Low-Cost Sensors; Reference Methods, Microsensors, Experimental Campaign &#160; Abstract:Air quality in the Middle East (ME) is strongly affected by desert dust besides anthropogenic pollutants. The health hazards associated with particulate matter (PM) are the most severe in this desert region. The enhancement of Air quality monitoring is needed to implement abatement strategies and stimulate environmental awareness among citizens. Several techniques are used to monitor PM concentration. The air quality monitoring stations (AQMS) equipped with certified instrumentation is the most reliable option. However, AQMSs are quite expensive and require regular maintenance. Another option is low-cost sensors (LCS) that seen as&#160;innovative&#160;tools for future smart cities. They are cost-effective and allow to increase the spatial coverage of air-quality measurements as the number of conventional AQMS is generally quite small, so the current density of the monitoring stations in the Middle East is low. In this work, we evaluated the PM air-quality climatology in the major cities in Saudi Arabia (Jeddah, Riyadh, and Dammam) for four years between 2016 and continued until 2020. We used the measurement data that were conducted by&#160;the Saudi Authority for Industrial Cities and Technology Zones (MODON)&#160;using certified reference AQMS installed inside the suburban areas of the three major cities in Saudi Arabia. Also, we tested the performance of the five LCS systems for eight months, starting in May 2019 and continued until January 2020. For this purpose, we set AQMS with the PM reference instrumentation (based on beta-ray absorption) side-by-side with five different LCS systems (based on light scattering) in the industrial part of Jeddah city. We collected, filtered, validated PM data, and applied standard measurement and calibration procedures. The AQMS measurements show that in Summer, the daily mean PM concentrations exceed the World Health Organization (WHO) limits for PM2.5 and PM10 almost every day in Jeddah, Riyadh, and Dammam. The WHO limits are also frequently violated in the winter months. The AQMS measurements reliably show dust storm spikes when PM pollution is extremely high while all the LCSs fail to capture these severe events. We found that LCS and AQMS PM measurements are poorly correlated in Summer, but show slightly better results in fair-weather Winter days when humidity and temperature are low. But they still cannot capture severe dust events.

Download Full-text

Developing Relative Humidity and Temperature Corrections for Low-Cost Sensors Using Machine Learning

Sensors ◽

10.3390/s21103338 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3338

Author(s):

Ivan Vajs ◽

Dejan Drajic ◽

Nenad Gligoric ◽

Ilija Radovanovic ◽

Ivan Popovic

Keyword(s):

Machine Learning ◽

Air Quality ◽

Relative Humidity ◽

Low Cost ◽

Quality Monitoring ◽

Air Quality Monitoring ◽

Lower Accuracy ◽

Wide Range ◽

The Impact ◽

Monitoring Stations

Existing government air quality monitoring networks consist of static measurement stations, which are highly reliable and accurately measure a wide range of air pollutants, but they are very large, expensive and require significant amounts of maintenance. As a promising solution, low-cost sensors are being introduced as complementary, air quality monitoring stations. These sensors are, however, not reliable due to the lower accuracy, short life cycle and corresponding calibration issues. Recent studies have shown that low-cost sensors are affected by relative humidity and temperature. In this paper, we explore methods to additionally improve the calibration algorithms with the aim to increase the measurement accuracy considering the impact of temperature and humidity on the readings, by using machine learning. A detailed comparative analysis of linear regression, artificial neural network and random forest algorithms are presented, analyzing their performance on the measurements of CO, NO2 and PM10 particles, with promising results and an achieved R2 of 0.93–0.97, 0.82–0.94 and 0.73–0.89 dependent on the observed period of the year, respectively, for each pollutant. A comprehensive analysis and recommendations on how low-cost sensors could be used as complementary monitoring stations to the reference ones, to increase spatial and temporal measurement resolution, is provided.

Download Full-text

Long-term evaluation and calibration of three types of low-cost PM2.5 sensors at different air quality monitoring stations

Journal of Aerosol Science ◽

10.1016/j.jaerosci.2021.105829 ◽

2021 ◽

pp. 105829

Author(s):

Gung-Hwa Hong ◽

Thi-Cuc Le ◽

Jing-Wei Tu ◽

Chieh Wang ◽

Shuenn-Chin Chang ◽

...

Keyword(s):

Air Quality ◽

Low Cost ◽

Quality Monitoring ◽

Air Quality Monitoring ◽

Term Evaluation ◽

Air Quality Monitoring Stations ◽

Monitoring Stations

Download Full-text

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

ACM Transactions on Sensor Networks ◽

10.1145/3446005 ◽

2021 ◽

Vol 17 (2) ◽

pp. 1-44

Author(s):

Francesco Concas ◽

Julien Mineraud ◽

Eemil Lagerspetz ◽

Samu Varjonen ◽

Xiaoli Liu ◽

...

Keyword(s):

Machine Learning ◽

Air Quality ◽

Environmental Monitoring ◽

Low Cost ◽

Quality Monitoring ◽

Machine Learning Techniques ◽

Future Research ◽

Great Promise ◽

Air Quality Monitoring ◽

Monitoring Stations

The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence, environmental monitoring stations are typically sparsely deployed, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve the granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: They suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors, such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Periodic re-calibration can improve the accuracy of low-cost sensors, particularly with machine-learning-based calibration, which has shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.

Download Full-text

Wireless Sensors Network Monitoring of Saharan Dust Events in Bari, Italy

Proceedings ◽

10.3390/proceedings2130898 ◽

2018 ◽

Vol 2 (13) ◽

pp. 898 ◽

Cited By ~ 1

Author(s):

Michele Penza ◽

Domenico Suriano ◽

Valerio Pfister ◽

Mario Prato ◽

Gennaro Cassano

Keyword(s):

Air Quality ◽

Low Cost ◽

Cost Effective ◽

Saharan Dust ◽

Quality Monitoring ◽

Sensor Data ◽

Air Quality Monitoring ◽

Dust Events ◽

Air Quality Monitoring Stations ◽

Monitoring Stations

A sensors network based on 8 stationary nodes distributed in Bari (Southern Italy) hasbeen deployed for urban air quality monitoring during advection events of Saharan dust in theperiod 2015–2017. The low-cost sensor-systems have been installed in specific sites (buildings,offices, schools, streets, airport) to assess the PM10 concentration at high spatial and temporalresolution in order to supplement the expensive official air monitoring stations for citizen sciencepurposes. Continuous measurements were performed by a cost-effective optical particle counter(PM10), including temperature and relative humidity sensors. They are operated to assess theperformance during a long-term campaign (July 2015–December 2017) of 30 months for smart citiesapplications. The sensor data quality has been evaluated by comparison to the reference data of the9 Air Quality Monitoring Stations (AQMS), managed by local environmental agency (ARPA-Puglia)in the Bari city.

Download Full-text

Forecasting Model Validation of Particulate Air Pollution by Low Cost Sensors Data

Journal of Modeling and Optimization ◽

10.32732/jmo.2019.11.2.63 ◽

2019 ◽

Vol 11 (2) ◽

pp. 63-68 ◽

Cited By ~ 1

Author(s):

Nicoletta Lotrecchiano ◽

Filomena Gioiella ◽

Aristide Giuliano ◽

Daniele Sofia

Keyword(s):

Air Quality ◽

Urban Areas ◽

Low Cost ◽

Emission Control ◽

Quality Monitoring ◽

Forecasting Model ◽

Air Quality Monitoring ◽

Monitoring Networks ◽

Human Beings ◽

Monitoring Stations

Environmental pollution in urban areas may be mainly attributed to the rapid industrialization and increased growth of vehicular traffic. As a consequence of air quality deterioration, the health and welfare of human beings are compromised. Air quality monitoring networks usually are used not only to assess the pollutant trend but also in the effective set-up of preventive measures of atmospheric pollution. In this context, monitoring can be a valid action to evaluate different emission control scenarios; however, installing a high space-time resolution monitoring network is still expensive. Merge of observations data from low-cost air quality monitoring networks with forecasting models can contribute to improving significantly emission control scenarios. In this work, a validation algorithm of the forecasting model for the concentration of small particulates (PM10 and PM2.5) is proposed. Results showed a satisfactory agreement between the PM concentration forecast values and the measured data from 3 air quality monitoring stations. Final average RMSE values for all monitoring stations are equal to about 4.5 µg/m3.

Download Full-text

On the Security and Data Integrity of Low-Cost Sensor Networks for Air Quality Monitoring

Sensors ◽

10.3390/s18124451 ◽

2018 ◽

Vol 18 (12) ◽

pp. 4451 ◽

Cited By ~ 10

Author(s):

Lan Luo ◽

Yue Zhang ◽

Bryan Pearson ◽

Zhen Ling ◽

Haofei Yu ◽

...

Keyword(s):

Air Quality ◽

Low Cost ◽

Measurement Data ◽

Data Integrity ◽

Pollution Monitoring ◽

Quality Monitoring ◽

Monitoring Systems ◽

Air Quality Monitoring ◽

Air Pollution Monitoring ◽

The Public

The emerging connected, low-cost, and easy-to-use air quality monitoring systems have enabled a paradigm shift in the field of air pollution monitoring. These systems are increasingly being used by local government and non-profit organizations to inform the public, and to support decision making related to air quality. However, data integrity and system security are rarely considered during the design and deployment of such monitoring systems, and such ignorance leaves tremendous room for undesired and damaging cyber intrusions. The collected measurement data, if polluted, could misinform the public and mislead policy makers. In this paper, we demonstrate such issues by using a.com, a popular low-cost air quality monitoring system that provides an affordable and continuous air quality monitoring capability to broad communities. To protect the air quality monitoring network under this investigation, we denote the company of interest as a.com. Through a series of probing, we are able to identify multiple security vulnerabilities in the system, including unencrypted message communication, incompetent authentication mechanisms, and lack of data integrity verification. By exploiting these vulnerabilities, we have the ability of “impersonating” any victim sensor in the a.com system and polluting its data using fabricated data. To the best of our knowledge, this is the first security analysis of low-cost and connected air quality monitoring systems. Our results highlight the urgent need in improving the security and data integrity design in these systems.

Download Full-text